From e290141439b60d387c3719dbb54efe3fcd7a41b4 Mon Sep 17 00:00:00 2001 From: Christian Pointner Date: Sun, 6 Nov 2022 22:45:38 +0100 Subject: monitoring/prometheus: improve grafana dashboard for smokeping-prober --- .../prometheus/server/defaults/main/rules_smokeping.yml | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'roles/monitoring/prometheus/server/defaults/main/rules_smokeping.yml') diff --git a/roles/monitoring/prometheus/server/defaults/main/rules_smokeping.yml b/roles/monitoring/prometheus/server/defaults/main/rules_smokeping.yml index 5bab05f1..6dfcd2f9 100644 --- a/roles/monitoring/prometheus/server/defaults/main/rules_smokeping.yml +++ b/roles/monitoring/prometheus/server/defaults/main/rules_smokeping.yml @@ -1,6 +1,15 @@ --- prometheus_server_rules_smokeping_extra: [] prometheus_server_rules_smokeping: + - record: instance:smokeping_probe_success:ratio1m + expr: increase(smokeping_response_duration_seconds_count[1m]) / increase(smokeping_requests_total[1m]) + - record: instance:smokeping_response_duration_seconds:q50 + expr: histogram_quantile(0.50, rate(smokeping_response_duration_seconds_bucket[1m])) + - record: instance:smokeping_response_duration_seconds:q90 + expr: histogram_quantile(0.90, rate(smokeping_response_duration_seconds_bucket[1m])) + - record: instance:smokeping_response_duration_seconds:q99 + expr: histogram_quantile(0.99, rate(smokeping_response_duration_seconds_bucket[1m])) + - alert: SmokepingProberConfigReloadFailure expr: smokeping_prober_config_last_reload_successful != 1 for: 0m -- cgit v1.2.3